MCP SSH Gateway
io.github.d00mus/mcp-ssh-gateway
SSH terminals for AI agents: stateful shells, exit codes the moment a command ends, router CLIs.
Install surfaces
How MCP SSH Gateway runs, per the official MCP registry entry.
Governed execution
How KLA gates calls to MCP SSH Gateway once it is connected.
A published policy defines which MCP SSH Gateway actions an agent may take and under what conditions. Each call passes through a policy gate at the tool-call boundary. Permitted actions execute, with the policy basis recorded. Flagged actions execute and are sampled for scheduled human review. High-stakes actions pause and route to a named reviewer on the Decision Desk. The call, the policy decision, and any approval are sealed as an evidence record.
KLA also governs the agents and model providers you already run. See integrations.